Skip to content

tangle-network/agent-runtime

View on GitHub ↗Related repositories →

The engine for running and improving AI agents. Run loops, analyze traces automatically, and feed learnings back into agents continuously to improve them.

active 2026-05-032026-08-10 (UTC)

Partial coverage12,452 / 14,160 hourly files (88%) · 2 absent upstream · 1,703 failed, retryable2024-12-292026-08-11 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
712
Pushes
318
Pull requests
41
Issues
0
Stars
0
Forks
0

Activity over time

Daily event counts in the loaded window

Line chart, 100 days from 2026-05-03 to 2026-08-10. Pushes: 318 total, peak 17 in a day. Pull requests: 41 total, peak 4 in a day. Issues: 0 total, peak 0 in a day. Comments: 10 total, peak 2 in a day. Stars: 0 total, peak 0 in a day.

  • Pushes
  • Pull requests
  • Issues
  • Comments
  • Stars

Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.

Top contributors

Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity

ContributorContributionsPushesPRsComments
drewstone316276332
tangletools833584
Tjemmmic10703
rpelevin1001

Recent activity

Latest issues, pull requests and releases

  • Pull request#471drewstone2026-07-04 22:07
  • Pull request#447drewstone2026-07-02 22:34
  • Pull request#433drewstone2026-07-02 00:14
  • Pull request#430drewstone2026-07-01 05:27
  • Pull request#420drewstone2026-06-30 21:37
  • Pull request#416drewstone2026-06-30 01:37
  • Issue comment#408drewstone2026-06-29 04:58
    feat(bench): add external benchmark adapters for WebArena, tau-bench, DABStep, AgentBench, and ToolLLM
  • Pull request#403drewstone2026-06-28 03:13
  • Pull request#402drewstone2026-06-28 02:15
  • Pull request#397drewstone2026-06-26 21:56
  • Pull request#388drewstone2026-06-25 17:39
  • Issue comment#384Tjemmmic2026-06-25 03:11
    fix(examples): exclude the optional-peer researcher-loop from the examples typecheck
  • Pull request#364drewstone2026-06-22 18:02
  • Issue comment#346drewstone2026-06-19 21:37
    feat(runtime): durable run loop — wire supervisor resume + journal the kernel loop
  • Pull request#302drewstone2026-06-14 22:33
  • Pull request#301drewstone2026-06-14 22:11
  • Pull request#288drewstone2026-06-14 01:13
  • Issue comment#123rpelevin2026-06-12 01:14
    Migrate agents off ::: fenced-block parsing → approval-gated tool calls
  • Pull request#261drewstone2026-06-11 14:36
  • Pull request#258drewstone2026-06-11 01:45
  • Pull request#255drewstone2026-06-11 00:23
  • Issue comment#222tangletools2026-06-10 11:19
    docs: reconcile vision docs with the measured evidence state
  • Pull request#207drewstone2026-06-09 22:43
  • Pull request#203drewstone2026-06-09 10:43
  • Pull request#193drewstone2026-06-07 21:54

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 0 stars here means stars gained during the window, not the repo's star count.